Training in progress, step 90, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:05a0608a0d108d197d5820e3b216e8d7a09ddb76226408ab8f49c2438e9fb16d
+oid sha256:91a3b29856143aecc3a1fd76b949ca0dd86fb486460a8825bb04011135aea6da
 size 90207248

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:761ab0ea9c61d6e62dfbe008243dbfa326d67c392160d21b091f12b6a9a11a62
+oid sha256:efdd3a8541cf52ef664e6919d0834665f7aee03a1cc90078eecd7f50255b8cf0
 size 46057082

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:597c452dbb6d2e2055a44445aa9e337aa4085eacd11fcbc7213a5eb6f6055867
+oid sha256:63c9cc0f3c04b2c00adeda1f5d60d230e61e99e3404c96ea1e859f8d4e96fa90
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7803647d52fbd7429a283dc695ba7cf653ff890c06d5c50f67d0a09610438889
+oid sha256:23b27ab0ae2b9af6f3d4c84cdaf8b0fc887acf71f8f726b270a3bce2845000a9
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": 1.602448582649231,
   "best_model_checkpoint": "miner_id_24/checkpoint-80",
-  "epoch": 0.022590893046240734,
+  "epoch": 0.025414754677020826,
   "eval_steps": 10,
-  "global_step": 80,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -639,6 +639,84 @@
       "eval_samples_per_second": 5.584,
       "eval_steps_per_second": 5.584,
       "step": 80
+    },
+    {
+      "epoch": 0.022873279209318743,
+      "grad_norm": 1.699086308479309,
+      "learning_rate": 0.0001898168561213419,
+      "loss": 1.3892,
+      "step": 81
+    },
+    {
+      "epoch": 0.02315566537239675,
+      "grad_norm": 1.2091821432113647,
+      "learning_rate": 0.0001895331334332753,
+      "loss": 1.5162,
+      "step": 82
+    },
+    {
+      "epoch": 0.023438051535474763,
+      "grad_norm": 1.6631978750228882,
+      "learning_rate": 0.0001892457303887706,
+      "loss": 0.8076,
+      "step": 83
+    },
+    {
+      "epoch": 0.02372043769855277,
+      "grad_norm": 1.577644944190979,
+      "learning_rate": 0.0001889546588018412,
+      "loss": 1.4393,
+      "step": 84
+    },
+    {
+      "epoch": 0.02400282386163078,
+      "grad_norm": 1.207412838935852,
+      "learning_rate": 0.00018865993063730004,
+      "loss": 2.1015,
+      "step": 85
+    },
+    {
+      "epoch": 0.02428521002470879,
+      "grad_norm": 2.7810745239257812,
+      "learning_rate": 0.00018836155801026753,
+      "loss": 1.4547,
+      "step": 86
+    },
+    {
+      "epoch": 0.024567596187786797,
+      "grad_norm": 2.054161787033081,
+      "learning_rate": 0.0001880595531856738,
+      "loss": 1.3083,
+      "step": 87
+    },
+    {
+      "epoch": 0.02484998235086481,
+      "grad_norm": 3.753908634185791,
+      "learning_rate": 0.00018775392857775432,
+      "loss": 2.8305,
+      "step": 88
+    },
+    {
+      "epoch": 0.025132368513942818,
+      "grad_norm": 4.611723899841309,
+      "learning_rate": 0.00018744469674953956,
+      "loss": 1.7302,
+      "step": 89
+    },
+    {
+      "epoch": 0.025414754677020826,
+      "grad_norm": 2.27549409866333,
+      "learning_rate": 0.00018713187041233896,
+      "loss": 1.8115,
+      "step": 90
+    },
+    {
+      "epoch": 0.025414754677020826,
+      "eval_loss": 1.6072229146957397,
+      "eval_runtime": 133.6033,
+      "eval_samples_per_second": 5.584,
+      "eval_steps_per_second": 5.584,
+      "step": 90
     }
   ],
   "logging_steps": 1,
@@ -653,7 +731,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -667,7 +745,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7830428681502720.0,
+  "total_flos": 8809232266690560.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null